Strategies for training optical neural networks

被引：0
|
作者：
Qipeng Yang [1 ]
Bowen Bai [1 ]
Weiwei Hu [1 ]
Xingjun Wang [1 ,2 ,3 ,4 ]
机构：
[1] State Key Laboratory of Advanced Optical Communications System and Networks, School of Electronics, Peking University
[2] Yangtze Delta Institute of Optoelectronics, Peking University
[3] Frontiers Science Center for Nano-optoelectronics, Peking University
[4] Peng Cheng Laboratory
来源：
National Science Open | 2022年 / 1卷 / 03期
基金：
中国博士后科学基金; 中国国家自然科学基金;
关键词：
D O I：
暂无
中图分类号：
TP183 [人工神经网络与计算];
学科分类号：
摘要：
Deep learning has flourished in different areas in recent years, such as computer vision and natural language processing. However, with the end of Moore’s law, these applications that rely heavily on computing power are facing bottlenecks. Optical neural networks(ONNs) [1] use light to perform calculations [2,3] featuring high speed and low energy consumption, and they are widely regarded as the next-generation application-specific integrated circuit(ASIC) [4,5] for artificial intelligence.
引用
收藏
页码：7 / 11
页数：5
相关论文
共 50 条
  • [1] Hybrid training of optical neural networks
    Spall, James
    Guo, Xianxin
    Lvovsky, A., I
    OPTICA, 2022, 9 (07): : 803 - 811
  • [2] Exploring Strategies for Training Deep Neural Networks
    Larochelle, Hugo
    Bengio, Yoshua
    Louradour, Jerome
    Lamblin, Pascal
    JOURNAL OF MACHINE LEARNING RESEARCH, 2009, 10 : 1 - 40
  • [3] Exploring strategies for training deep neural networks
    Larochelle, Hugo
    Bengio, Yoshua
    Louradour, Jérôme
    Lamblin, Pascal
    Journal of Machine Learning Research, 2009, 10 : 1 - 40
  • [4] Efficient training of unitary optical neural networks
    Lu, Kunrun
    Guo, Xianxin
    OPTICS EXPRESS, 2023, 31 (24) : 39616 - 39623
  • [5] Training Strategies for Convolutional Neural Networks with Transformed Input
    Khandani, Masoumeh Kalantari
    Mikhael, Wasfy B.
    2021 IEEE INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2021, : 1058 - 1061
  • [6] CONVOLUTIONAL NEURAL NETWORKS AND TRAINING STRATEGIES FOR SKIN DETECTION
    Kim, Yoonsik
    Hwang, Insung
    Cho, Nam Ik
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3919 - 3923
  • [7] In situ optical backpropagation training of diffractive optical neural networks
    TIANKUANG ZHOU
    LU FANG
    TAO YAN
    JIAMIN WU
    YIPENG LI
    JINGTAO FAN
    HUAQIANG WU
    XING LIN
    QIONGHAI DAI
    Photonics Research , 2020, (06) : 940 - 953
  • [8] In situ optical backpropagation training of diffractive optical neural networks
    Zhou, Tiankuang
    Fang, Lu
    Yan, Tao
    Wu, Jiamin
    Li, Yipeng
    Fan, Jingtao
    Wu, Huaqiang
    Lin, Xing
    Dai, Qionghai
    PHOTONICS RESEARCH, 2020, 8 (06) : 940 - 953
  • [9] In situ optical backpropagation training of diffractive optical neural networks
    TIANKUANG ZHOU
    LU FANG
    TAO YAN
    JIAMIN WU
    YIPENG LI
    JINGTAO FAN
    HUAQIANG WU
    XING LIN
    QIONGHAI DAI
    Photonics Research, 2020, 8 (06) : 940 - 953
  • [10] Fully forward mode training for optical neural networks
    Xue, Zhiwei
    Zhou, Tiankuang
    Xu, Zhihao
    Yu, Shaoliang
    Dai, Qionghai
    Fang, Lu
    NATURE, 2024, 632 (8024) : 280 - 286
12345